{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T13:04:20Z","timestamp":1771074260526,"version":"3.50.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013091","name":"Science and Technology Major Project of Guangxi","doi-asserted-by":"publisher","award":["AB21196029"],"award-info":[{"award-number":["AB21196029"]}],"id":[{"id":"10.13039\/501100013091","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51979228"],"award-info":[{"award-number":["51979228"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52102469"],"award-info":[{"award-number":["52102469"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Basic Scientific Research Program","award":["JCKY2019207A019"],"award-info":[{"award-number":["JCKY2019207A019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Instrum. Meas."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tim.2023.3273687","type":"journal-article","created":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T18:42:09Z","timestamp":1683571329000},"page":"1-12","source":"Crossref","is-referenced-by-count":5,"title":["Learning End-to-End Visual Servoing Using an Improved Soft Actor-Critic Approach With Centralized Novelty Measurement"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1181-4531","authenticated-orcid":false,"given":"Jian","family":"Gao","sequence":"first","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4671-8371","authenticated-orcid":false,"given":"Yaozhen","family":"He","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-1443","authenticated-orcid":false,"given":"Yimin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0634-6734","authenticated-orcid":false,"given":"Yufeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.03.045"},{"key":"ref35","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2913321"},{"key":"ref34","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"Proc 23rd AAAI Conf Artif Intell"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2021.11.009"},{"key":"ref37","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2475376"},{"key":"ref36","author":"lecun","year":"2010","journal-title":"The MNIST Database of Handwritten Digits"},{"key":"ref31","article-title":"Go-explore: A new approach for hard-exploration problems","author":"ecoffet","year":"2019","journal-title":"arXiv 1901 10995"},{"key":"ref30","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","author":"badia","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.04.028"},{"key":"ref33","first-page":"1","article-title":"Experience selection in deep reinforcement learning for control","volume":"29","author":"bruin","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989442"},{"key":"ref32","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/70.760345"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.250573"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2865004"},{"key":"ref39","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2617464"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2908923"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.2991147"},{"key":"ref24","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"bellemare","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"93","article-title":"How can we define intrinsic motivation?","author":"oudeyer","year":"2008","journal-title":"Proc 8th Int Conf Epigenetic Robot Modeling Cogn Develop Robot Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref25","first-page":"4","volume":"30","author":"tang","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594249"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341756"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3057005"},{"key":"ref28","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"stadie","year":"2015","journal-title":"arXiv 1507 00814"},{"key":"ref27","article-title":"Exploration by random network distillation","author":"burda","year":"2018","journal-title":"arXiv 1810 12894"},{"key":"ref29","article-title":"Never give up: Learning directed exploration strategies","author":"badia","year":"2020","journal-title":"arXiv 2002 06038"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197196"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968216"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3033794"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3147867"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561070"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341758"}],"container-title":["IEEE Transactions on Instrumentation and Measurement"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/19\/10012124\/10121359.pdf?arnumber=10121359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:07:21Z","timestamp":1686593241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10121359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/tim.2023.3273687","relation":{},"ISSN":["0018-9456","1557-9662"],"issn-type":[{"value":"0018-9456","type":"print"},{"value":"1557-9662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}